Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (which only say not read-only, not open-world, not destructive), the description reveals crucial behavior: report and openGraph are merged by sub-key, systemText is replaced rather than optionally, outcome removal is rejected while still referenced, and image fields accept media IDs, URLs, or empty strings to clear. This fully explains subtle mutation semantics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The main description is dense but each sentence earns its place by communicating high-level merge/clear/language/reference rules before descending into sub-fields. The structure could be slightly simplified but is appropriately informative for a complex update endpoint.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With nested objects, scene-dependent rules, image upload flows, and wholesale-vs-merge semantics, this description covers the most important constraints: how sub-fields behave, how to clear values, what is immutable, and what sibling tools handle related concerns. The output schema is present, so return-value details are already known; nothing critical is omitted.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already covers 100% of parameters with detailed descriptions, so the baseline is 3; the description adds cross-field semantics not obvious from schema alone, such as merge-by-key behavior, wholesale replacement, and scene-specific rejected operations. It is highly valuable but largely reinforces details already present in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Update a form of the current team') and enumerates the exact fields that can be updated. It also explicitly routes Question management and dimensionAnalysis to sibling tools, clearly distinguishing this tool's scope from alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-not guidance: questions go through add_question/update_question etc., dimensionAnalysis alone through set_dimension_analysis, and language is only changeable under certain conditions. It also clarifies that scene cannot be changed at all and references finalize_image_upload for image inputs, leaving little to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.